In [74]:
# Importing libraries
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import explained_variance_score,mean_absolute_error,r2_score,mean_absolute_percentage_error
# Dropping irrelevant columns for training the model
x_features = df_final.drop(['Income', 'IncomeErr', 'IncomePerCap', 'IncomePerCapErr',"City","State","RaceOther"], axis=1)
y_output = df_final['Income']
# Diving the data into training and testing dataset
x_train, x_test, y_train, y_test = train_test_split(x_features, y_output, shuffle=True)
# Building a linear regression model
model=LinearRegression()
model.fit(x_train, y_train)
# Predicting on test data
y_pred = model.predict(x_test)
# Model performance evaluation
print("\tMean absolute error:", mean_absolute_error(y_test, y_pred))
print("\tR2 score:", r2_score(y_test, y_pred))
print(mean_absolute_percentage_error(y_test, model.predict(x_test)))
plt.figure()
ax1 = sns.distplot(y_test, hist=False, color="r", label="Actual Value")
sns.distplot(y_pred, hist=False, color="b", label="Predicted Values" , ax=ax1, )
plt.title('Actual (Red) vs Predicted (Blue) Income')
plt.xlabel('Income')
plt.ylabel('Income')
plt.show()
plt.close()
Mean absolute error: 9668.872091027031 R2 score: 0.6912387735814876 0.17908434488282726
